Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to the word "one" and its various usages in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lex
    -0.15
    ze
    -0.15
    sez
    -0.15
    rick
    -0.15
     Pul
    -0.15
     object
    -0.15
    UTE
    -0.15
    atch
    -0.14
    ates
    -0.14
    sm
    -0.14
    POSITIVE LOGITS
    652
    0.16
    645
    0.15
     Dank
    0.15
    pollo
    0.14
    asal
    0.14
    .updateDynamic
    0.14
    HeaderCode
    0.14
    plier
    0.14
    ÑĢив
    0.14
    รส
    0.14
    Act Density 0.026%

    No Known Activations